A Novel Segmentation Recognition Algorithm of Agaricus bisporus Based on Morphology and Iterative Marker-Controlled Watershed Transform

Accurate recognition of Agaricus bisporus is a prerequisite for precise automatic harvesting in factory environment. Aimed at segmenting mushrooms adhering together from the complex background, this paper proposes watershed-based segmentation algorithm A. bisporus. First, foreground extracted via Otsu threshold and morphological operations. Then, preliminary novel iterative marker generation method are proposed to prepare watershed markers. On basis, marker-controlled adopted segment recognize individuals. All algorithms implemented based on OpenCV (Open Source Computer Vision) libraries. Tests images collected cultivation bed show that average correct rate 95.7%, diameter measurement error 1.15%, coordinate deviation 1.43%. The processing time 705.7 ms per single image, satisfying real-time constraints 1 image/s. performed better than current Circle Hough Transform (OpenCV’s implementation). It convenient easy operate, providing sound basis subsequent research mechanized equipment